Singing Voice Separation Using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy

12/04/2018
by   Kin Wah Edward Lin, et al.
0

Separating a singing voice from its music accompaniment remains an important challenge in the field of music information retrieval. We present a unique neural network approach inspired by a technique that has revolutionized the field of vision: pixel-wise image classification, which we combine with cross entropy loss and pretraining of the CNN as an autoencoder on singing voice spectrograms. The pixel-wise classification technique directly estimates the sound source label for each time-frequency (T-F) bin in our spectrogram image, thus eliminating common pre- and postprocessing tasks. The proposed network is trained by using the Ideal Binary Mask (IBM) as the target output label. The IBM identifies the dominant sound source in each T-F bin of the magnitude spectrogram of a mixture signal, by considering each T-F bin as a pixel with a multi-label (for each sound source). Cross entropy is used as the training objective, so as to minimize the average probability error between the target and predicted label for each pixel. By treating the singing voice separation problem as a pixel-wise classification task, we additionally eliminate one of the commonly used, yet not easy to comprehend, postprocessing steps: the Wiener filter postprocessing. The proposed CNN outperforms the first runner up in the Music Information Retrieval Evaluation eXchange (MIREX) 2016 and the winner of MIREX 2014 with a gain of 2.2702 5.9563 dB global normalized source to distortion ratio (GNSDR) when applied to the iKala dataset. An experiment with the DSD100 dataset on the full-tracks song evaluation task also shows that our model is able to compete with cutting-edge singing voice separation systems which use multi-channel modeling, data augmentation, and model blending.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/24/2021

Deep Learning Approach for Singer Voice Classification of Vietnamese Popular Music

Singer voice classification is a meaningful task in the digital era. Wit...
research
06/20/2019

Adversarial Learning for Improved Onsets and Frames Music Transcription

Automatic music transcription is considered to be one of the hardest pro...
research
09/02/2017

A Recurrent Encoder-Decoder Approach with Skip-filtering Connections for Monaural Singing Voice Separation

The objective of deep learning methods based on encoder-decoder architec...
research
12/06/2017

Beyond the Pixel-Wise Loss for Topology-Aware Delineation

Delineation of curvilinear structures is an important problem in Compute...
research
02/01/2018

MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation

Monaural singing voice separation task focuses on the prediction of the ...
research
03/28/2022

Improved singing voice separation with chromagram-based pitch-aware remixing

Singing voice separation aims to separate music into vocals and accompan...
research
11/04/2017

Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask

Singing voice separation based on deep learning relies on the usage of t...

Please sign up or login with your details

Forgot password? Click here to reset